• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.4
• /
• pp.107-113
• /
• 2023

This paper proposes a method for detecting smoking behavior in images using artificial intelligence technology. Since smoking is not a static phenomenon but an action, the object detection technology was combined with the posture estimation technology that can detect the action. A smoker detection learning model was developed to detect smokers in images, and the characteristics of smoking behaviors were applied to posture estimation technology to detect smoking behaviors in images. YOLOv8 was used for object detection, and OpenPose was used for posture estimation. In addition, when smokers and non-smokers are included in the image, a method of separating only people was applied. The proposed method was implemented using Google Colab NVIDEA Tesla T4 GPU in Python, and it was found that the smoking behavior was perfectly detected in the given video as a result of the test.

• Advances in concrete construction
• /
• v.14 no.3
• /
• pp.185-194
• /
• 2022

For producing cement and concrete, the construction field has been encouraged by the usage of industrial soil waste (or) secondary materials since it decreases the utilization of natural resources. Simultaneously, for ensuring the quality, the analyses of the strength along with durability properties of that sort of cement and concrete are required. The prediction of strength along with other properties of High-Performance Concrete (HPC) by optimization and machine learning algorithms are focused by already available research methods. However, an error and accuracy issue are possessed. Therefore, the Enhanced Deep Neural Network (EDNN) based strength along with durability prediction of HPC was utilized by this research method. Initially, the data is gathered in the proposed work. Then, the data's pre-processing is done by the elimination of missing data along with normalization. Next, from the pre-processed data, the features are extracted. Hence, the data input to the EDNN algorithm which predicts the strength along with durability properties of the specific mixing input designs. Using the Switched Multi-Objective Jellyfish Optimization (SMOJO) algorithm, the weight value is initialized in the EDNN. The Gaussian radial function is utilized as the activation function. The proposed EDNN's performance is examined with the already available algorithms in the experimental analysis. Based on the RMSE, MAE, MAPE, and R² metrics, the performance of the proposed EDNN is compared to the existing DNN, CNN, ANN, and SVM methods. Further, according to the metrices, the proposed EDNN performs better. Moreover, the effectiveness of proposed EDNN is examined based on the accuracy, precision, recall, and F-Measure metrics. With the already-existing algorithms i.e., JO, GWO, PSO, and GA, the fitness for the proposed SMOJO algorithm is also examined. The proposed SMOJO algorithm achieves a higher fitness value than the already available algorithm.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.271-281
• /
• 2022

Manual seed classification challenges can be overcome using a reliable and autonomous seed purity identification and classification technique. It is a highly practical and commercially important requirement of the agricultural industry. Researchers can create a new data mining method with improved accuracy using current machine learning and artificial intelligence approaches. Seed classification can help with quality making, seed quality controller, and impurity identification. Seeds have traditionally been classified based on characteristics such as colour, shape, and texture. Generally, this is done by experts by visually examining each model, which is a very time-consuming and tedious task. This approach is simple to automate, making seed sorting far more efficient than manually inspecting them. Computer vision technologies based on machine learning (ML), symmetry, and, more specifically, convolutional neural networks (CNNs) have been widely used in related fields, resulting in greater labour efficiency in many cases. To sort a sample of 3000 seeds, KNN, SVM, CNN and CNN-SVM hybrid classification algorithms were used. A model that uses advanced deep learning techniques to categorise some well-known seeds is included in the proposed hybrid system. In most cases, the CNN-SVM model outperformed the comparable SVM and CNN models, demonstrating the effectiveness of utilising CNN-SVM to evaluate data. The findings of this research revealed that CNN-SVM could be used to analyse data with promising results. Future study should look into more seed kinds to expand the use of CNN-SVMs in data processing.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• Archives of design research
• /
• v.16 no.4
• /
• pp.37-46
• /
• 2003

About 18th century in the late Chosun dynasty, various kinds of 'Min-Wha' had played a significant role and had an important meaning in the lives of the people in that period. Therefore, both in material and in technique, so many diversified 'Min-Wha' were mass produced in that time. Starting from those backgrounds, 'Hyuk-Wha', is considered as one of unique style of expression. Though, 'Hyuk-Wha', in techniques, was originated from 'Bibaekseo' classified as one of the style of expression in Oriental drawing and writing art. 'Hyuk-Wha' shows and expresses visual differentiation from rough 'Bibaekseo', in substance, written by brush made from the skin of a willow tree or the stem of a sort of reeds. 'Hyuk-Wha', in mode, has very dose relation to the process of the development of 'Min-Wha'. Judging from this point of view, 'Hyuk-Wha' has deep relationship to Taosmic character painting of 'Gilsang: an auspicious sign' or Confucian character painting of 'Hyojae: filial piety. Accordingly, 'Hyuk-Wha' has been developed to that character painting designed by another type of creative differentiations. For these reasons, 'Hyuk-Wha' which significantly shapes and contains the meanings of Chinese Character also has been esteemed to have interrelation with Pictography in application of Word mark or Brand logotype in graphic areas. 'Hyuk-Wha' which was prevalent in use of home decorations for the people existed in the past has been ceased to exist nowadays in use of home decorations by appearance of all sort of decoration articles. All these days, 'Hyuk-Wha' which was diversified as a part 'Min-Wha' and developed together with oriental drawing and writing art and character painting is to be necessarily relighted. And 'Hyuk-Wha', which is also vigorously in practical application in Western Europe is desirable to be reconsidered.

• The Journal of the Korea Contents Association
• /
• v.18 no.11
• /
• pp.277-284
• /
• 2018

The purpose of this study was to investigate the Q - method, which is one of the qualitative analysis methods to approach deep and intrinsic meaning about the perception of college students about food in traditional market. Recently, local governments have been developing diverse tourism products aimed at young people in order to revitalize traditional markets. In this study, we classify the perception of food in traditional market by university students, And to suggest strategic implications by using it as basic data for establishing marketing strategy so that young people can visit in the futures. In order to analyze the perception of college students' subjective perception of traditional market food, Factor analysis was used to conduct an exploratory study. To do this, a Q-sort, Program, and Q factor analysis. The results were classified into three types. The first type (N = 21): Memories seeking type, the second type (N = 6): Local culture resource seeking type, the third type(N = 5). Each of these subjective perceptions can be used as a basis for future research. Through the establishment of marketing strategies for each of the three types of classifications, the direction of traditional markets is presented, and a variety of food items that are valuable as local tourism resources are accommodated by accepting university students' to contribute to the revitalization of traditional markets.

• Journal of Conservation Science
• /
• v.4 no.1 s.4
• /
• pp.3-10
• /
• 1995

This study focused on the reconstructional point of Shinan ship-wreck that was excavated between $1976\~1984$. The wreck, which might be sunk in the beginning of the 14th century, is regarded as a vessel of Yuan dynasty, China. This paper tried to find out some structural characteristics and principal dimensions for restoration. The Shinan shipwreck's structural characteristics are summarized as follow, 1) The Shinan shipwreck is formed V-shaped cross section with bar keel, 2) The vessel is divided 8 holds by 7 bulkheads. 3) The ship has flat type stem and transome stern. 4) A rabbeted clinker -built is basically adopted on planking joint. 5) A wooden sheathing, which means a sort of protecting board against marine insects, is covered outside of the main hull, 6) For making an watertight structure, oakum and lime mixtured t'ung-oil are used along the seam of planking and bulkhead. 7) A V-shaped deep water-way exists at both deck side. 8) The shipwreck is believed to have 2 masts at least. 9) The shiptimbers are classified as Chinese Red Pine(Pinus Massonina) which is mainly grown in the southern part of China. Considering as mentioned above the structural characteristics, Shinan ship-wreck could be classified as Chinese Fu-chuan type(복선형) of sea-going ship. The Shinan ship's principal dimensions which are calculated on the basis of Chinese traditional shipbuilding custom, are as follow, Length overall(L.O.A). : 34.80m Length water line(L.W.L) : 24.90m Breadth(B.max.) : 11m Breadth(B) : 10m Depth at keel line(H) : 3.75m Draft(D). : 3.15m Freeboard(F) : 0.65m Ratio, length/breadth(L/B). : 2.26 Ration, breadth/depth(B/D) : 3.5 Height of stem : 7m Height of stern : 10m Displacement : ab.340ton.

• Journal of the Korea Convergence Society
• /
• v.10 no.6
• /
• pp.15-24
• /
• 2019

The development of "New Retailing" is still in its infancy. Theoretical research has just begun, showing the characteristics of practice leading theoretical research, that is, there is more practical exploration but relatively insufficient theoretical research. At present, the theoretical research and practice development of "New Retailing" is gradually clear. The future development trend is large-scale, no boundaries, and wisdom. The academic community should further study in depth with theory and practice, focusing on the deep integration of online and offline, the new logistics under "New Retailing", and the research direction of "New Retailing" driving supply chain transformation and reconstruction so as to better guide the development of "New Retailing". The purpose of the research is to sort out the research status and theoretical situation of "new retailing", so as to provide references for further research on "new retail" and guidance for practical development.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.483-483
• /
• 2022

댐과 저수지의 운영 최적화를 위한 수문학적 예보는 현재 수동적인 댐 운영이 주를 이루면서 활용도가 높지 않다. 불확실한 기후변화나 기후재난 상황에서 우리 사회에 악영향을 최소화하기 위해 선제적으로 대응/대비할 수 있는 댐 운영 방안이 불가피하다. 강우량 예측 기술은 기후변화로 인해 제한적인 상황이다. 실례로, 2020년 8월에 섬진강의 댐이 극심한 집중 강우로 인해 무너지는 사태가 발생하였고 이로 인해 지역사회에 막대한 경제적 피해가 발생하였다. 선제적 댐 방류량 운영 기술은 또한 환경적인 변화로 인한 영향을 완화하기 위해 필요한 것이다. 제한적인 기상 예보 기술을 극복하고자 심화학습이나 강화학습 같은 인공지능 모델들의 활용성에 대한 연구가 시도되고 있다. 따라서 본 연구는 섬진강 댐의 시간당 수문 데이터를 이용하여 댐 운영을 위한 심화학습 모델을 개발하고 그 활용도를 평가하였다. 댐 운영을 위한 심화학습 모델로서 시계열 데이터 예측에 적합한 Long Sort Term Memory(LSTM)과 Gated Recurrent Unit(GRU) 알고리즘을 구축하고 댐 수위를 예측하였다. 분석 자료는 WAMIS에서 제공하는 2000년부터 2021년까지의 시간당 데이터를 사용하였다. 입력 데이터로서 시간당 유입량, 강우량과 방류량을, 출력 데이터로서 시간당 수위 자료를 각각 사용하였으며. 결정계수(R2 Score)를 통해 모델의 예측 성능을 평가하였다. 댐 수위 예측값 개선을 위해 하이퍼파라미터의 '최적값'이 존재하는 범위를 줄여나가는 하이퍼파라미터 최적화를 두 가지 방법으로 진행하였다. 첫 번째 방법은 수동적 탐색(Manual Search) 방법으로 Sequence Length를 24, 48, 72시간, Hidden Layer를 1, 3, 5개로 설정하여 하이퍼파라미터의 조합에 따른 LSTM와 GRU의 민감도를 평가하였다. 두 번째 방법은 Grid Search로 최적의 하이퍼파라미터를 찾았다. 이 두가지 방법에서는 같은 하이퍼파라미터 안에서 GRU가 LSTM에 비해 더 높은 예측 정확도를 보였고 Sequence Length가 높을수록 정확도가 높아지는 경향을 보였다. Manual Search 방법의 경우 R2가 최대 0.72의 정확도를 보였고 Grid Search 방법의 경우 R2가 0.79의 정확도를 보였다. 본 연구 결과는 가뭄과 홍수와 같은 물 재해에 사전 대응하고 기후변화에 적응할 수 있는 댐 운영 개선에 도움을 줄 수 있을 것으로 판단된다.

• Journal of the Korean Society for Library and Information Science
• /
• v.51 no.4
• /
• pp.99-120
• /
• 2017

In order to develop a semiautomatic support system that allows researchers concerned to efficiently analyze the technical trends for the ever-growing industry and market. This paper introduces a couple of Korean sentence generation models that can automatically generate definitional statements as well as descriptions of technical terms and concepts. The proposed models are based on a deep learning model called LSTM (Long Sort-Term Memory) capable of effectively labeling textual sequences by taking into account the contextual relations of each item in the sequences. Our models take technical terms as inputs and can generate a broad range of heterogeneous textual descriptions that explain the concept of the terms. In the experiments using large-scale training collections, we confirmed that more accurate and reasonable sentences can be generated by CHAR-CNN-LSTM model that is a word-based LSTM exploiting character embeddings based on convolutional neural networks (CNN). The results of this study can be a force for developing an extension model that can generate a set of sentences covering the same subjects, and furthermore, we can implement an artificial intelligence model that automatically creates technical literature.